© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 12095
    Prev
    Next
    INDEX
    Explanations

    names of political figures with middle eastern origins

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly focusing on Muammar Gaddafi and related names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Skydragon
    -0.67
     FSA
    -0.66
     rake
    -0.63
     ILCS
    -0.62
     BASE
    -0.61
     Flavoring
    -0.61
     BIG
    -0.58
    STE
    -0.57
     puzz
    -0.57
     iP
    -0.57
    POSITIVE LOGITS
    vu
    0.83
    warm
    0.82
    emort
    0.79
    heed
    0.79
    iors
    0.76
    ña
    0.75
    itte
    0.74
    jen
    0.73
    friend
    0.70
    idad
    0.69
    Activations Density 0.103%

    No Known Activations